Published on Mon Jan 20 2020

Short Text Classification via Term Graph

Wei Pang

Short text is limited in shortness in text length. This leads to a challenging problem of sparse features. Most of existing methods treat each short sentences as independently and identically distributed.

0
0
0
Abstract

Short text classi cation is a method for classifying short sentence with prede ned labels. However, short text is limited in shortness in text length that leads to a challenging problem of sparse features. Most of existing methods treat each short sentences as independently and identically distributed (IID), local context only in the sentence itself is focused and the relational information between sentences are lost. To overcome these limitations, we propose a PathWalk model that combine the strength of graph networks and short sentences to solve the sparseness of short text. Experimental results on four different available datasets show that our PathWalk method achieves the state-of-the-art results, demonstrating the efficiency and robustness of graph networks for short text classification.

Sat Apr 14 2018
Artificial Intelligence
ClassiNet -- Predicting Missing Features for Short-Text Classification
The fundamental problem in short-text classification is the lack of feature overlap. We propose a network of classifiers trained for predicting missing features in a given instance. We show that ClassiNets generalize word co-occurrence graphs. We extract numerous features from the trained ClassiNet to overcome feature sparseness.
0
0
0
Tue Sep 11 2018
NLP
Topic Memory Networks for Short Text Classification
Many classification models work poorly on short texts due to data sparsity. We propose a novel topic memory mechanism to encode latent topic representations indicative of class labels. Experimental results show that our model outperforms state-of-the-art models on short text.
0
0
0
Wed Dec 17 2014
NLP
Word Network Topic Model: A Simple but General Solution for Short and Imbalanced Texts
The short text has been the prevalent format for information of Internet in recent decades. Its extreme sparsity and imbalance brings unprecedented challenges to conventional topic models like LDA and its variants. WNTM is a word co-occurrence network based model to tackle the sparsity.
0
0
0
Thu Mar 26 2020
Machine Learning
Bag of biterms modeling for short texts
Short texts do not provide enough context information, causing the failure of the traditionalStatistical models. This paper presents a novel framework, namely Bag of Biterms Modeling (BBM), for modeling massive, dynamic, and short text Collections.
0
0
0
Mon Mar 09 2015
Neural Networks
Syntax-based Deep Matching of Short Texts
Deep Match Tree is a new approach to the problem of matching two sentences or two short texts. The approach consists of two components, a mining algorithm to discover patterns and a deep neural network.
0
0
0
Mon Sep 16 2019
NLP
Short-Text Classification Using Unsupervised Keyword Expansion
Short-text classification, like all data science, struggles to achieve high performance using limited data. As a solution, a short sentence may be expanded with new and relevant feature words to form an artificially enlarged dataset. The word generation process was assessed by examining how well the predicted words matched to topics.
0
0
0